Project 1

library("tidyverse")

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

library("ggplot2")
library("ggrepel")
library("ggcorrplot")
library("DT")
library("dplyr")

cases <- read_csv("COVID-19_cases_plus_census.csv")

Rows: 3142 Columns: 259── Column specification ───────────────────────────────────────────────────────────────────
Delimiter: ","
chr    (5): county_fips_code, county_name, state, state_fips_code, geo_id
dbl  (243): confirmed_cases, deaths, nonfamily_households, family_households, median_ye...
lgl   (10): pop_5_years_over, speak_only_english_at_home, speak_spanish_at_home, speak_...
date   (1): date
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

cases

cases <- cases %>% mutate_if(is.character, factor)
dim(cases)

[1] 3142  259

cases_high <- cases %>% filter(confirmed_cases > 300000)
dim(cases_high)

[1]   4 259

summary(cases_high[,1:10])

 county_fips_code             county_name     state   state_fips_code      date            confirmed_cases  
 04013  :1        Cook County       :1    AZ     :1   04     :1       Min.   :2021-01-19   Min.   : 347965  
 06037  :1        Los Angeles County:1    CA     :1   06     :1       1st Qu.:2021-01-19   1st Qu.: 406374  
 12086  :1        Maricopa County   :1    FL     :1   12     :1       Median :2021-01-19   Median : 430866  
 17031  :1        Miami-Dade County :1    IL     :1   17     :1       Mean   :2021-01-19   Mean   : 553078  
 01001  :0        Abbeville County  :0    AK     :0   01     :0       3rd Qu.:2021-01-19   3rd Qu.: 577570  
 01003  :0        Acadia Parish     :0    AL     :0   02     :0       Max.   :2021-01-19   Max.   :1002614  
 (Other):0        (Other)           :0    (Other):0   (Other):0                                             
     deaths          geo_id  nonfamily_households family_households
 Min.   : 4622   04013  :1   Min.   : 272813      Min.   : 585476  
 1st Qu.: 5988   06037  :1   1st Qu.: 453163      1st Qu.: 878560  
 Median : 7494   12086  :1   Median : 643445      Median :1079603  
 Mean   : 8386   17031  :1   Mean   : 662745      Mean   :1237151  
 3rd Qu.: 9892   01001  :0   3rd Qu.: 853027      3rd Qu.:1438194  
 Max.   :13936   01003  :0   Max.   :1091276      Max.   :2203922  
                 (Other):0                                         

ggplot(cases_high, mapping = aes(confirmed_cases)) + geom_histogram(bins = 10)